Anticipation in collaborative music performance using fuzzy systems: a case study
This work addresses the challenge of human-AI collaboration in creative domains like music, though it is incremental as it builds on existing fuzzy systems and focuses on a specific case study without broad SOTA claims.
The authors tackled the problem of enabling AI systems to exhibit anticipatory behavior in collaborative music performance by designing a fuzzy logic-based system to control a virtual drummer's parameters in response to a human pianist's playing. The result is a case study outlining the methodology and design, with an evaluation in public concerts planned but not yet conducted.
In order to collaborate and co-create with humans, an AI system must be capable of both reactive and anticipatory behavior. We present a case study of such a system in the domain of musical improvisation. We consider a duo consisting of a human pianist accompained by an off-the-shelf virtual drummer, and we design an AI system to control the perfomance parameters of the drummer (e.g., patterns, intensity, or complexity) as a function of what the human pianist is playing. The AI system utilizes a model elicited from the musicians and encoded through fuzzy logic. This paper outlines the methodology, design, and development process of this system. An evaluation in public concerts is upcoming. This case study is seen as a step in the broader investigation of anticipation and creative processes in mixed human-robot, or "anthrobotic" systems.